genoffice
Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI agent, plus a `genoffice` CLI and agent skill so Claude Code, Codex and Cursor can create and edit real .docx/.xlsx/.pptx files locally. Bring your own key. macOS, Windows & Linux.
Runssource: GitHubhomepageTypeScriptApache-2.0commit 69b4ce0560a7
TypeScript, Apache-2.0 licensed. The project labels itself: ai, ai agent, claude code, cli, codex, cursor, docx and excel.
genoffice runs. An Argusic agent installed it in 1.5 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 18 workspace packages build and pass their unit tests (8300+ tests), the Electron shell launches on the virtual display producing a 1279x799 'GenOffice' window, and 40 end-to-end functional tests drive the real built app through document editing flows including docs, sheets, markdown, PDF, and slides.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 97.3 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- 5 docs visual regression tests fail: 2305-7617 pixel diffs on committed baselines5 minutes
- Cargo/Rust toolchain not found (needed by sheets xlsx sidecar)1 minute
- Node v18 was installed; repo requires >=22.120.5 minutes
- unzip command not found (used by e2e tests to verify xlsx content)0.5 minutes
- zip command not found (used by e2e tests to build .xlsx and .pptx fixtures)0.5 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 60 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- Unit tests: `npm test`, all 18 workspaces pass (docx-engine: 1118 passed/1 skipped, pdf2docx: 699/7, pptx-engine: 868, pptx-render: 254, docs: 1846, sheets: 2329/1, slides: 699/12, shell: 224, pdf: 674, markdown: 164, plus i18n/electron-utils/font-metrics/file-parse/ai-search/agent-core/ai-provider/project-store and 6 Rust sidecar tests; 8300+ total). Typecheck: `npm run typecheck`, all 19 workspaces pass. E2E: `npx playwright test e2e/`, 40 functionally passing tests drive the real built Electron shell through docs, sheets (edit/save/csv-export/insert/ribbon/xlsm), markdown, PDF, slides, and theme flows on Xvfb display. 5 docs visual regression tests fail due to font-stack metrics mismatch (documented environmental gap).
- Model tokens used
- 835,962
- Exact commit tested
- 69b4ce0560a7
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec
/bin/sh -lc 'cd /work/repo && export PATH=/home/runner/tools:$HOME/.cargo/bin:$PATH && export PATH=…
succeeded in 288175ms:
e2e/docs-visual.spec.ts:63:9 › docs visual regression › captable-inline renders pixel-identical…
e2e/docs-visual.spec.ts:63:9 › docs visual regression › captable-float renders pixel-identical …
e2e/docs-visual.spec.ts:63:9 › docs visual regression › captable-pct renders pixel-identical pa…
e2e/docs-visual.spec.ts:63:9 › docs visual regression › captable-page-anchor renders pixel-iden…
40 passed (4.8m)
Now I have complete data for the final report.
tokens used
835,962
Now I have complete data for the final report.Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 1.5 minutes, faster than the median of the 136 comparable projects Argusic has measured.
- Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 3 times, so the result is not a one-off.
Of the 137 agent projects Argusic has installed and timed, genoffice was the 21st fastest to reach a running state, and 89 of 137 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 1.5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
aiai-agentclaude-codeclicodexcursordocxexcellibreoffice-alternativelocal-firstmarkdown-editormicrosoft-office-alternativeoffice-suitepdf-editorpdf-to-wordpowerpointpptxskillsspreadsheetxlsx
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/genoffice)Questions
- Does genoffice run?
- Yes. genoffice runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test genoffice?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 69b4ce0560a7. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test genoffice?
- The run that produced this verdict cost $0.25: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does genoffice take to install?
- 1.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does genoffice need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing genoffice?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does genoffice compare with the alternatives?
- Of the 137 agent projects Argusic has installed and timed, genoffice was the 21st fastest to reach a running state, and 89 of 137 reached one at all.
- Where is the evidence for genoffice?
- All 3 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.